{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T03:30:14Z","timestamp":1782876614732,"version":"3.54.5"},"reference-count":29,"publisher":"World Scientific Pub Co Pte Ltd","issue":"02","funder":[{"name":"Beijing Information Science and Technology University \u201cQin-Xin Talent\u201d Cultivation Project","award":["QXTCP C201906"],"award-info":[{"award-number":["QXTCP C201906"]}]},{"name":"Beijing Information Science and Technology University Research Level Improvement Project","award":["2020KYNH214"],"award-info":[{"award-number":["2020KYNH214"]}]},{"name":"Science and Technology Project of the Beijing Municipal Education Commission","award":["KM201811232016"],"award-info":[{"award-number":["KM201811232016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Model. Simul. Sci. Comput."],"published-print":{"date-parts":[[2022,4]]},"abstract":"<jats:p> Deep neural network (DNN) models have been widely used in e-commerce, games, automobiles, manufacturing, and so on. Improper structure, parameters, activation function, or incorrect loss function of the DNN models may cause defects in performance or security. As a result, there are some researches that focus on repairing DNN such as MODE and Apricot. However, the cost of repairing is high or the repair may lead to overfitting. In order to solve this problem, we propose GenMuNN, which is a Mutation-Based Approach to Repair Deep Neural Network Models. First, it analyzes the importance of the weights of the neurons in each layer of the DNN model to the correctness of the final prediction results, and ranks the weights according to the influence on the prediction results of the DNN model. Second, mutation is performed to generate mutants based on the rank of weights, and genetic algorithms are used to select mutants for the next round of mutation until the stop condition is touched. Experiments are carried on a set of DNN models which are trained with the MNIST dataset. The experimental results show that GenMuNN can improve the accuracy of the DNN models. <\/jats:p>","DOI":"10.1142\/s1793962323410088","type":"journal-article","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T11:46:25Z","timestamp":1647258385000},"source":"Crossref","is-referenced-by-count":11,"title":["GenMuNN: A mutation-based approach to repair deep neural network models"],"prefix":"10.1142","volume":"13","author":[{"given":"Huanhuan","family":"Wu","sequence":"first","affiliation":[{"name":"Computer School, Beijing Information Science, and Technology University, Beijing, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Li","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science, and Technology University, Beijing, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5537-9236","authenticated-orcid":false,"given":"Zhanqi","family":"Cui","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science, and Technology University, Beijing, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbin","family":"Liu","sequence":"additional","affiliation":[{"name":"Computer School, Beijing Information Science, and Technology University, Beijing, P. R. China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"219","published-online":{"date-parts":[[2022,3,12]]},"reference":[{"key":"S1793962323410088BIB001","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"S1793962323410088BIB002","first-page":"6","volume-title":"CVPR Workshops","author":"Narodytska N.","year":"2017"},{"key":"S1793962323410088BIB003","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248110"},{"issue":"6","key":"S1793962323410088BIB004","first-page":"345","volume":"5","author":"Neeraja M.","year":"2015","journal-title":"Int. J. Sci. Res."},{"key":"S1793962323410088BIB005","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1145\/3368555.3384468","volume-title":"Proc. ACM Conf. Health, Inference, and Learning","author":"Oakden-Rayner L.","year":"2020"},{"key":"S1793962323410088BIB006","first-page":"588","volume-title":"Proc. 42nd ACM SIGPLAN Int. Conf. Programming Language Design and Implementation","author":"Sotoudeh M.","year":"2021"},{"issue":"1","key":"S1793962323410088BIB009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3105906","volume":"51","author":"Monperrus M.","year":"2018","journal-title":"ACM Comput. Surveys"},{"key":"S1793962323410088BIB010","first-page":"175","volume-title":"Proc. 2018 26th ACM Joint Meeting on European Software Engineering Conf. Symp. Foundations of Software Engineering","author":"Ma S.","year":"2018"},{"key":"S1793962323410088BIB011","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1145\/3324884.3416624","volume-title":"Proc. 35th IEEE\/ACM Int. Conf. Automated Software Engineering","author":"Chen J.","year":"2020"},{"key":"S1793962323410088BIB012","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1109\/ICSE.2013.6606626","volume-title":"2013 35th Int. Conf. Software Engineering (ICSE)","author":"Kim D.","year":"2013"},{"issue":"1","key":"S1793962323410088BIB013","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1109\/TSE.2011.104","volume":"38","author":"Le Goues C.","year":"2011","journal-title":"IEEE Trans. Softw. Eng."},{"key":"S1793962323410088BIB015","first-page":"3","volume-title":"2012 34th Int. Conf. Software Engineering (ICSE)","author":"Le Goues C.","year":"2012"},{"key":"S1793962323410088BIB016","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1109\/ASE.2019.00043","volume-title":"2019 34th IEEE\/ACM Int. Conf. Automated Software Engineering (ASE)","author":"Zhang H.","year":"2019"},{"key":"S1793962323410088BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2010.62"},{"key":"S1793962323410088BIB018","first-page":"1135","volume-title":"2020 IEEE\/ACM 42nd Int. Conf. Software Engineering (ICSE)","author":"Islam M. J.","year":"2020"},{"key":"S1793962323410088BIB019","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1145\/3238147.3238172","volume-title":"Proc. 33rd ACM\/IEEE Int. Conf. Automated Software Engineering","author":"Sun Y.","year":"2018"},{"key":"S1793962323410088BIB020","first-page":"4901","volume-title":"Int. Conf. Machine Learning","author":"Odena A.","year":"2019"},{"key":"S1793962323410088BIB021","first-page":"146","volume-title":"Proc. 28th ACM SIGSOFT Int. Symp. Software Testing and Analysis","author":"Xie X.","year":"2019"},{"key":"S1793962323410088BIB022","first-page":"851","volume-title":"Proc. 28th ACM Joint Meeting on European Software Engineering Conf. Symp. Foundations of Software Engineering","author":"Harel-Canada F.","year":"2020"},{"key":"S1793962323410088BIB023","first-page":"775","volume-title":"Proc. 28th ACM Joint Meeting on European Software Engineering Conf. Symp. Foundations of Software Engineering","author":"Yan S.","year":"2020"},{"key":"S1793962323410088BIB024","first-page":"165","volume-title":"Proc. 29th ACM SIGSOFT Int. Symp. Software Testing and Analysis","author":"Lee S.","year":"2020"},{"key":"S1793962323410088BIB025","first-page":"177","volume-title":"Proc. 29th ACM SIGSOFT Int. Symp. Software Testing and Analysis","author":"Feng Y.","year":"2020"},{"key":"S1793962323410088BIB026","first-page":"826","volume-title":"Proc. 28th ACM Joint Meeting on European Software Engineering Conf. Symp. Foundations of Software Engineering","author":"Zhang Y.","year":"2020"},{"key":"S1793962323410088BIB027","first-page":"1630","volume-title":"Proc. 28th ACM Joint Meeting on European Software Engineering Conf. Symp. Foundations of Software Engineering","author":"Li R.","year":"2020"},{"key":"S1793962323410088BIB028","first-page":"1699","volume-title":"Proc. 28th ACM Joint Meeting on European Software Engineering Conf. Symp. Foundations of Software Engineering","author":"Tian Y.","year":"2020"},{"key":"S1793962323410088BIB029","first-page":"1147","volume-title":"2020 IEEE\/ACM 42nd Int. Conf. Software Engineering (ICSE)","author":"Gao X.","year":"2020"},{"key":"S1793962323410088BIB030","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.enbuild.2013.10.016","volume":"69","author":"Moon J. W.","year":"2014","journal-title":"Energy Build."},{"issue":"7","key":"S1793962323410088BIB031","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1145\/2856103","volume":"59","author":"Roychoudhury A.","year":"2016","journal-title":"Commun. ACM"},{"key":"S1793962323410088BIB034","doi-asserted-by":"crossref","first-page":"730","DOI":"10.1109\/DSA52907.2021.00106","volume-title":"2021 IEEE 8th Int. Conf. on Dependable Systems and Their Applications (DSA)","author":"Wu H.","year":"2021"}],"container-title":["International Journal of Modeling, Simulation, and Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S1793962323410088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,18]],"date-time":"2022-05-18T11:34:34Z","timestamp":1652873674000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S1793962323410088"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,12]]},"references-count":29,"journal-issue":{"issue":"02","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["10.1142\/S1793962323410088"],"URL":"https:\/\/doi.org\/10.1142\/s1793962323410088","relation":{},"ISSN":["1793-9623","1793-9615"],"issn-type":[{"value":"1793-9623","type":"print"},{"value":"1793-9615","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,12]]},"article-number":"2341008"}}